Litcius/Paper detail

GACA: A Gradient-Aware and Contrastive-Adaptive Learning Framework for Low-Light Image Enhancement

Zishu Yao, Jian-Nan Su, Guodong Fan, Min Gan, C. L. Philip Chen

2024IEEE Transactions on Instrumentation and Measurement28 citationsDOI

Abstract

Image gradients contain crucial information in the images. However, the gradient information of low-light images is often concealed in darkness and is susceptible to noise contamination. This imprecise gradient information poses a significant obstacle to Low-Light Image Enhancement (LLIE) tasks. Simultaneously, methods relying solely on pixel-level reconstruction loss struggle to accurately correct the mapping from dimly lit images to normal images, resulting in restored outcomes with color abnormalities or artifacts. In this paper, we propose a Gradient-Aware and Contrastive-Adaptive (GACA) Learning Framework to address the aforementioned issues. GACA initially estimates more accurate gradient information and employs it as a structural prior to guide image generation. Simultaneously, we introduce a novel regularization constraint to better rectify the image mapping. Extensive experiments on benchmark datasets and downstream segmentation tasks demonstrate state-of-the-art performance and generalization. Compared to existing approaches, our method achieves an average 4.7% reduction in NIQE on benchmark datasets. The code is available at https://github.com/iijjlk/GACA.

Topics & Concepts

Artificial intelligenceComputer scienceBenchmark (surveying)PixelCode (set theory)Computer visionImage restorationConstraint (computer-aided design)SegmentationImage (mathematics)Regularization (linguistics)Pattern recognition (psychology)Image processingMathematicsGeographySet (abstract data type)GeometryProgramming languageGeodesyImage Enhancement TechniquesAdvanced Image Processing TechniquesAdvanced Vision and Imaging